Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 31363
    Prev
    Next
    INDEX
    Explanations

    mentions of first-time historic achievements or records related to individuals in political positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Invoker
    -0.16
    iot
    -0.16
    AndView
    -0.15
     putas
    -0.15
    undle
    -0.14
    CRET
    -0.14
    ãĤ¤ãĥī
    -0.14
    Mahon
    -0.14
     Fame
    -0.14
    InRange
    -0.13
    POSITIVE LOGITS
     ever
    0.27
    -ever
    0.25
    ever
    0.24
     openly
    0.24
     woman
    0.24
     female
    0.21
     person
    0.21
     زÙĨÛĮ
    0.19
    female
    0.19
     elected
    0.18
    Activations Density 0.055%

    No Known Activations